Hybrid Deep Intelligence for Aircraft Engine Remaining Useful Life Prediction

DOI

10.2991/978-94-6239-713-2_35How to use a DOI?

Keywords

Remaining Useful Life Prediction; CMAPSS dataset; FD001; Predictive Maintenance; Neural State Space Model

Abstract

In modern aerospace systems, reliability-centered maintenance promotes the implementation of condition-based maintenance to ensure operational safety and enable precise lifespan estimation of aircraft engines. This study investigates RUL prediction using the FD001(subset of C-MAPSS) of NASA prognostics repository simulated dataset. The FD001 subset comprises nonlinear time-series sensor measurements from turbines under diverse operating states and degradation trajectories. A deep neural state-space modelling framework is proposed to capture the latent degradation dynamics governing engine health evolution. The method explicitly simulates the relationship between observable sensor measurements and concealed state transitions. To enhance the model performance and training stability, the feature selection technique called Shapley Additive exPlanations is implemented to filter the informative sensors, critical prognostic indicator identification, and signal elimination. To capture the nonlinear dynamics of aircraft engines, the LSTM-based state-space model incorporates batch normalization, dropout regularization, and early stopping techniques. The Neural State Space model integrates physics-informed state-space modeling with neural architectures, achieving improved Remaining Useful Life prediction with Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and NASA scoring metrics compared to baseline models.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - J. Porkavi
AU  - Kalpanapriya Dhakshnamoorthy
PY  - 2026
DA  - 2026/06/25
TI  - Hybrid Deep Intelligence for Aircraft Engine Remaining Useful Life Prediction
BT  - Proceedings of the International Conference on Advances in Computing Technology and Artificial Intelligence (COMPUTATIA 2026)
PB  - Atlantis Press
SP  - 468
EP  - 481
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-713-2_35
DO  - 10.2991/978-94-6239-713-2_35
ID  - Porkavi2026
ER  -